Power plant bucket wheel machine unmanned intelligent operation method and system based on AI algorithm

Abstract

The invention provides a power plant bucket wheel machine unmanned intelligent operation method and system based on an AI algorithm, and relates to the technical field of bucket wheel machines, and the method comprises the steps: obtaining the operation state information of a power plant and the information of the bucket wheel machine; constructing a power plant-bucket wheel machine digital twin model according to the power plant operation state information and the bucket wheel machine information; based on the power plant-bucket wheel machine digital twin model, correlation analysis of the power plant fuel reserve and the bucket wheel machine transportation task is carried out, and an optimized transportation scheme is obtained; performing discrete event simulation processing according to the optimized transportation scheme to obtain an efficiency simulation result; and performing optimization processing based on an efficiency simulation result, and obtaining an operation scheme by setting a target function and solving an optimal solution. Through future prediction of the state of the power plant equipment and modeling of the bucket wheel machine state transition probability matrix and the equipment cooperative working mode, the operation state of the equipment can be monitored and dynamically adjusted in real time, and the overall operation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of bucket wheel stacker reclaimers, and more specifically, to an unmanned intelligent operation method and system for a bucket wheel stacker reclaimer in a power plant based on an AI algorithm. Background Art

[0002] In modern power plants, bucket wheel stacker reclaimers, as important material conveying equipment, are widely used in operation tasks such as fuel transportation and ash handling. With the increasing global energy demand and the expansion of power plant scale, the working efficiency and reliability of bucket wheel stacker reclaimers play a crucial role in the stable operation of the entire power generation system. However, in the operation of traditional power plant bucket wheel stacker reclaimers, equipment control mainly relies on mechanical systems and manual intervention. Although this method can meet basic requirements in daily operation, with the improvement of technical requirements, the adaptability and efficiency of traditional systems face challenges. Current technologies often lack intelligent support in aspects such as real-time monitoring of equipment status, optimization of collaborative operations, and regulation of energy consumption. In particular, the collaborative operations between bucket wheel stacker reclaimers and other equipment and the planning of transportation routes mostly rely on preset programs and manual adjustments, lacking the ability of real-time dynamic optimization and intelligent decision-making. In addition, existing systems usually conduct equipment monitoring and maintenance based on a single physical model, failing to comprehensively consider the complex interactions between equipment, resulting in the inability of the system to respond quickly when equipment status or environmental changes occur, thereby affecting the overall production efficiency.

[0003] Based on the above disadvantages of the existing technology, there is an urgent need for an unmanned intelligent operation method and system for a power plant bucket wheel stacker reclaimer based on an AI algorithm. Summary of the Invention

[0004] The purpose of the present invention is to provide an unmanned intelligent operation method for a power plant bucket wheel stacker reclaimer based on an AI algorithm to improve the above problems. To achieve the above purpose, the technical solutions adopted by the present invention are as follows:

[0005] In a first aspect, the present application provides an unmanned intelligent operation method for a power plant bucket wheel stacker reclaimer based on an AI algorithm, including:

[0006] Obtain the operation status information of the power plant and the information of the bucket wheel stacker reclaimer. The power plant status information includes the fuel reserve, boiler load, steam turbine status, and power generation power, and the bucket wheel stacker reclaimer information includes the position information, transportation efficiency, material grasping amount, and equipment failure status of the bucket wheel stacker reclaimer;

[0007] According to the operation status information of the power plant and the information of the bucket wheel stacker reclaimer, by performing trend analysis and state change modeling on the equipment status of the power plant and the operation status of the bucket wheel stacker reclaimer, a digital twin model of the power plant - bucket wheel stacker reclaimer is constructed;

[0008] Based on the power plant-bucket wheel excavator digital twin model, the correlation between the power plant's fuel reserves and the bucket wheel excavator's transportation tasks is analyzed. The transportation route is simulated using a path planning algorithm. The loading and unloading efficiency and equipment coordination are evaluated in combination with real-time status data to obtain an optimized transportation plan.

[0009] Discrete event simulation is performed based on the optimized transportation plan. By converting the transportation process into discrete events and combining real-time equipment status data to perform data format conversion and event-driven simulation, efficiency simulation results are obtained.

[0010] Based on the efficiency simulation results, optimization processing is performed by setting an objective function, which includes maximizing transportation efficiency, minimizing equipment failure rate, optimizing energy consumption and minimizing environmental impact. A multi-objective optimization algorithm is used to perform a weighted combination of each objective, and the optimal solution is solved to obtain an operation plan.

[0011] Secondly, this application also provides an unmanned intelligent operation system for bucket wheel excavators in power plants based on AI algorithms, including:

[0012] an acquisition module for acquiring power plant operating status information and bucket wheel excavator information, wherein the power plant status information includes fuel reserve, boiler load, turbine status, and power generation; and the bucket wheel excavator information includes location information, transportation efficiency, material grabbing amount, and equipment failure status of the bucket wheel excavator;

[0013] A modeling module is used to construct a power plant-bucket wheel machine digital twin model by performing trend analysis and state change modeling on the power plant equipment status and the bucket wheel machine operating status based on the power plant operating status information and the bucket wheel machine information;

[0014] An analysis module, based on the power plant-bucket wheel excavator digital twin model, performs correlation analysis between the power plant's fuel reserves and the bucket wheel excavator's transportation tasks, simulates transportation routes using a path planning algorithm, and evaluates loading and unloading efficiency and equipment coordination using real-time status data to obtain an optimized transportation plan;

[0015] A simulation module is used to perform discrete event simulation processing based on the optimized transportation plan, converting the transportation process into discrete events and performing data format conversion and event-driven simulation in combination with real-time equipment status data to obtain efficiency simulation results;

[0016] The optimization module performs optimization processing based on the efficiency simulation results by setting an objective function, which includes maximizing transportation efficiency, minimizing equipment failure rate, optimizing energy consumption and minimizing environmental impact. A multi-objective optimization algorithm is used to perform a weighted combination of each objective, and the optimal solution is solved to obtain an operation plan.

[0017] The beneficial effects of the present invention are as follows:

[0018] Through the future prediction of the equipment status of the power plant, the modeling of the state transition probability matrix of the bucket wheel stacker-reclaimer, and the collaborative working mode of the equipment, the present invention can monitor the operation status of the equipment in real time and dynamically adjust it, effectively optimize the operation path and operation mode of the equipment, reduce unnecessary energy waste, and improve the overall operation efficiency; by comprehensively considering the collaborative working mode of the power plant equipment and the bucket wheel stacker-reclaimer, and using mechanical mechanics modeling and mechanics simulation technology, the high-efficiency collaboration between the equipment is realized, ensuring that the collaborative effect of each equipment is maximized, and enhancing the adaptability and working stability of the bucket wheel stacker-reclaimer in complex working environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a schematic flowchart of a method for unmanned intelligent operation of a bucket wheel stacker-reclaimer in a power plant based on an AI algorithm described in an embodiment of the present invention;

[0021] Figure 2 It is a schematic structural diagram of a system for unmanned intelligent operation of a bucket wheel stacker-reclaimer in a power plant based on an AI algorithm described in an embodiment of the present invention;

[0022] Figure 3 It is a schematic structural diagram of a device for unmanned intelligent operation of a bucket wheel stacker-reclaimer in a power plant based on an AI algorithm described in an embodiment of the present invention.

[0023] Reference numerals in the figure: 800, a device for unmanned intelligent operation of a bucket wheel stacker-reclaimer in a power plant based on an AI algorithm; 801, a processor; 802, a memory; 803, a multimedia component; 804, an I / O interface; 805, a communication component; 901, an acquisition module; 902, a modeling module; 903, an analysis module; 904, a simulation module; 905, an optimization module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. The components of the embodiments of the present invention usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0025] It should be noted that like reference numerals and letters denote like items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0026] Embodiment 1:

[0027] This embodiment provides an unmanned intelligent operation method for a power plant bucket wheel stacker-reclaimer based on an AI algorithm.

[0028] See Figure 1 , which shows that this method includes steps S100 to S500.

[0029] Step S100: Obtain the operation status information of the power plant and the bucket wheel stacker-reclaimer information. The power plant status information includes the fuel reserve, boiler load, steam turbine status, and power generation power. The bucket wheel stacker-reclaimer information includes the position information, transportation efficiency, material grabbing amount, and equipment failure status of the bucket wheel stacker-reclaimer;

[0030] It is understandable that the core task of this step is to obtain the real-time operation status information of the power plant and the bucket wheel stacker-reclaimer. This data provides the basis for subsequent status prediction, optimized scheduling, and intelligent decision-making. The status information of the power plant includes parameters such as fuel reserve, boiler load, steam turbine status, and power generation capacity. This information helps to evaluate the current operation ability and resource utilization of the power plant. For example, the fuel reserve determines the continuous operation time of the power plant, while the boiler load and steam turbine status directly affect power generation efficiency and energy consumption. The power generation capacity reflects the output ability and production efficiency of the power plant. These data not only help to predict the workload of the power plant but also provide data support for equipment maintenance and optimization. The information of the bucket wheel stacker-reclaimer includes position information, transportation efficiency, material grabbing quantity, and equipment failure status. The position information is used to determine the real-time position of the bucket wheel stacker-reclaimer during the conveying process. The transportation efficiency and material grabbing quantity reflect the operation ability and performance of the bucket wheel stacker-reclaimer, and the equipment failure status can warn of potential failures and downtime problems. By combining this information, the collaborative operation status of the bucket wheel stacker-reclaimer and the power plant equipment can be accurately evaluated, and the operation plan can be adjusted in a timely manner according to the operation data to ensure the efficient and stable operation of the system.

[0031] In practical applications, modern sensors, Internet of Things (IoT) technology, and real-time data acquisition systems are used to monitor and update this information in real time to ensure the accuracy and timeliness of the data. The acquisition of this information provides accurate input data for the subsequent steps, enabling the system to respond according to real-time situations. By obtaining the status information of the power plant and the bucket wheel stacker-reclaimer in real time, dynamic operation scheduling and resource optimization can be achieved, avoiding the lag of traditional manual intervention, improving the predictability and efficiency of equipment operation, and reducing production losses caused by equipment failures or energy waste.

[0032] Step S200: According to the operation status information of the power plant and the information of the bucket wheel stacker-reclaimer, by performing trend analysis and state change modeling on the equipment status of the power plant and the operation status of the bucket wheel stacker-reclaimer, a digital twin model of the power plant-bucket wheel stacker-reclaimer is constructed;

[0033] It should be noted that the digital twin model can be updated in real time during the equipment operation process by combining big data collection, real-time monitoring systems, and AI algorithms. By combining traditional equipment monitoring methods with advanced predictive analysis methods, the decision-making for equipment operation and maintenance can make the best choice based on real-time data and future trends. By constructing the digital twin model in this step, global intelligent optimization of the power plant and bucket wheel stacker-reclaimer system can be achieved, accurately predicting equipment status, identifying potential failures in advance, thereby improving the stability of equipment operation, reducing downtime, and enhancing the resource utilization efficiency of the overall system.

[0034] Step S300: Conduct an association analysis of the fuel reserve in the power plant and the transportation tasks of the bucket wheel stacker-reclaimer based on the digital twin model of the power plant-bucket wheel stacker-reclaimer. Simulate the transportation route through a path planning algorithm, and evaluate the loading and unloading efficiency and the collaborative working conditions of the equipment by combining real-time status data to obtain an optimized transportation plan;

[0035] First of all, the association analysis is to model the relationship between the fuel reserve in the power plant and the transportation tasks of the bucket wheel stacker-reclaimer. Information such as the fuel reserve in the power plant and the boiler load determines the demand for the transportation tasks of the bucket wheel stacker-reclaimer. For example, when the fuel reserve decreases, the transportation tasks of the bucket wheel stacker-reclaimer need to be increased to ensure the continuous operation of the power plant; conversely, when the fuel reserve is sufficient, the demand for transportation tasks decreases. This association analysis uses multiple regression models, time series analysis, or machine learning methods to establish the connection between the resource requirements of the power plant and the tasks of the bucket wheel stacker-reclaimer, so as to provide accurate data input for path planning and transportation scheduling.

[0036] Next, path planning is to simulate the transportation path according to the digital twin model of the power plant-bucket wheel stacker-reclaimer and real-time status data, using optimization algorithms (such as A* algorithm, Dijkstra algorithm, or genetic algorithm). Path planning not only needs to consider the shortest distance of the transportation route, but also comprehensively consider factors such as equipment status, environmental conditions, and traffic flow in the operation area. For example, in the case of equipment failure or maintenance status, path planning needs to consider alternative paths or dynamically adjust the operation allocation of the equipment. In addition, real-time status data can also dynamically update the path planning results to cope with emergencies (such as equipment failures, weather changes, etc.). This path planning method ensures that the execution of transportation tasks can respond quickly according to the actual situation and improve transportation efficiency.

[0037] Finally, the evaluation of the loading and unloading efficiency and the collaborative working conditions of the equipment is to evaluate the loading and unloading efficiency and the collaborative effectiveness of the equipment by combining real-time equipment data and transportation path information. This process involves real-time monitoring of the equipment status (such as the grasping quantity and transportation speed of the bucket wheel stacker-reclaimer), and combining the collaborative working model to evaluate the collaborative working conditions of the bucket wheel stacker-reclaimer and other equipment in the power plant (such as conveyor belts, discharge ports, etc.). In the evaluation process, simulation technologies and performance analysis methods (such as Monte Carlo simulation or discrete event simulation) are used to simulate the equipment collaboration and loading and unloading efficiency under different paths, identify potential bottlenecks and optimize them. Finally, combining the path planning and the collaborative working conditions of the equipment, an optimized transportation plan is obtained to ensure the high efficiency and smoothness of the transportation process.

[0038] Step S400: Conduct discrete event simulation processing according to the optimized transportation plan. By converting the transportation process into discrete events and combining real-time equipment status data for data format conversion and event-driven simulation, an efficiency simulation result is obtained;

[0039] It is understandable that discrete event simulation processing transforms the entire transportation process into discrete events. By defining the time points and related conditions for each event occurrence, it simulates the actual operation process of the transportation task. Each transportation link (such as material loading, transportation, unloading, etc.) is regarded as an independent event. These events are discrete in time, and there can be a certain time interval between different events. During the simulation process, each event is triggered according to preset rules or real-time input data, thereby affecting the progress of the entire transportation process. For example, the failure of a certain component may cause a delay in the transportation task, or the occurrence of equipment failure will affect the operation path and transportation time. Through discrete event simulation, it is possible to simulate the timing relationship and state changes of each link in the transportation process, thus providing data support for subsequent optimization solutions. The final efficiency simulation results, that is, the evaluation results of different transportation schemes are generated through the simulation system. These results show the various efficiency indicators of the transportation process under different conditions, such as transportation time, equipment utilization rate, energy consumption, etc. Through simulation, potential bottleneck problems can be identified, such as unreasonable transportation routes, delays caused by equipment failures, etc., thereby providing a basis for further adjustment of the optimization plan. The simulation results can also help judge the performance of different optimization strategies in actual operation, providing a scientific basis for subsequent decision-making.

[0040] Step S500: Based on the efficiency simulation results, perform optimization processing. By setting an objective function, the objective function includes maximizing transportation efficiency, minimizing equipment failure rate, optimizing energy consumption, and minimizing environmental impact. Use a multi-objective optimization algorithm to perform weighted combination of each objective and solve for the optimal solution to obtain an operation plan.

[0041] It should be noted that the objective function is expressed as:

[0042] F total = w1·E transport - w2·F fault + w3·E energy - w4·E environment ;

[0043] Among them, F total represents the total objective; E transport represents transportation efficiency; F fault represents equipment failure rate; E energy represents energy consumption; E environment represents environmental impact; w1, w2, w3, and w4 respectively represent the weights of each index.

[0044] Subsequently, the optimal solution obtained through the multi-objective optimization algorithm can comprehensively consider the impacts of all objectives and give an optimal operation plan. This plan can not only improve transportation efficiency, reduce equipment failures, but also effectively reduce energy consumption and environmental impacts, ensuring the sustainability and high efficiency of the overall operation.

[0045] Further, step S200 includes step S210 to step S240.

[0046] Step S210: Conduct equipment status trend analysis based on the power plant operation status information. By using the autoregressive integrated moving average algorithm to perform trend analysis on the fuel reserve, boiler load, steam turbine status, and power generation of the power plant, the future predicted values of the power plant equipment status are obtained.

[0047] Specifically, first, the trend analysis predicts future trends by modeling the historical data of the power plant operation status. The operation status information of the power plant includes fuel reserve, boiler load, steam turbine status, and power generation, etc., which are all important factors affecting equipment operation efficiency and energy management. Using the ARIMA algorithm, these time series data can be modeled to capture the inherent laws and time dependencies of the data, thereby predicting the changes in equipment status within a certain period in the future. For example, by analyzing the historical data of boiler load and fuel reserve, the future energy demand and equipment load can be predicted, and the resource allocation can be adjusted according to the prediction results.

[0048] The ARIMA model is a classic time series prediction method, suitable for situations where the data has significant time dependencies and trend changes. It models the data through three key parts: autoregressive (AR) term, differencing (I) term, and moving average (MA) term. Specifically:

[0049] Autoregressive (AR): Assume that there is a linear relationship between the current value and the values at the previous few time points.

[0050] Differencing (I): By performing differencing on the time series, eliminate the non-stationarity in the data and make the mean and variance of the data stable.

[0051] Moving average (MA): By smoothing the past data error terms, reduce the impact of noise on the prediction results.

[0052] By using the ARIMA model to model the operation status data of the power plant (such as boiler load, fuel reserve, etc.), the predicted values of each key parameter within the future time period can be obtained. These predicted values can not only reflect the operation trends of the equipment, but also provide a basis for subsequent scheduling decisions. For example, predicting the future fuel demand and boiler load can effectively adjust the operation strategy of the power plant, perform resource allocation and equipment maintenance in advance, and ensure stable and efficient operation.

[0053] Step S220: Perform state change modeling based on the operation status information of the bucket wheel stacker-reclaimer. Model the state changes of the bucket wheel stacker-reclaimer by constructing a Hidden Markov Model (HMM), and simulate the operation state changes of the bucket wheel stacker-reclaimer to obtain the state transition probability matrix of the bucket wheel stacker-reclaimer.

[0054] It can be understood that the Hidden Markov Model is a statistical model that assumes that the state of the system is not directly observable (hidden state), but the state of the system can be inferred through some measurable variables (observation states) that can be observed. In this embodiment, the operation states of the bucket wheel stacker-reclaimer (such as normal operation, failure, standby, etc.) are considered as hidden states, while the real-time information of the monitoring equipment (such as transportation efficiency, grabbing quantity, equipment failure state, etc.) is used as observation states.

[0055] By constructing a Hidden Markov Model, the transition probability between different states of the bucket wheel stacker-reclaimer can be described. Specifically, the Hidden Markov Model includes the following main components:

[0056] State space: The possible working states of the bucket wheel stacker-reclaimer, such as "normal operation", "equipment failure", "standby", etc.

[0057] Transition probability matrix: Describes the probability of the bucket wheel stacker-reclaimer transferring from one state to another. For example, the probability of the bucket wheel stacker-reclaimer transferring from the "normal operation" state to the "equipment failure" state.

[0058] Observation probability: By monitoring the state of the equipment (such as grabbing quantity, transportation efficiency, etc.), estimate the probability of the observed results in each state.

[0059] The core task of the Hidden Markov Model is to estimate the state transition probability through historical data and predict future state changes based on these probabilities. By analyzing the historical operation data of the bucket wheel stacker-reclaimer (such as working states and related monitoring data), use the Maximum Likelihood Estimation (MLE) or Baum-Welch algorithm to estimate the transition probability, so as to obtain a state transition probability matrix. This matrix represents the transition probability between different states of the bucket wheel stacker-reclaimer and can provide data support for subsequent equipment management and optimal scheduling.

[0060] Furthermore, the generation process of the state transition probability matrix includes: modeling different operation states of the bucket wheel stacker-reclaimer, and extracting corresponding state transition records from historical data; using the learning algorithm of the Hidden Markov Model (such as the forward-backward algorithm) to calculate the transition probability between each state; the finally obtained transition probability matrix provides a quantitative description for the conversion between each state.

[0061] Finally, by constructing a Hidden Markov Model and obtaining the state transition probability matrix, the state change process of the bucket wheel stacker-reclaimer can be accurately simulated, providing predictive support for equipment maintenance, fault prediction, and scheduling. The state transition matrix can not only help evaluate the possible operating states of the bucket wheel stacker-reclaimer in the future period but also provide a basis for optimizing scheduling and resource allocation. For example, it can predict the likelihood of equipment failure based on the transition probability, enabling maintenance to be carried out in advance and reducing downtime. By modeling the state changes, the workload distribution of the equipment can be optimized, unnecessary equipment idle time can be reduced, and the operation efficiency can be improved.

[0062] Step S230: Obtain the historical data of the power plant equipment status and the bucket wheel stacker-reclaimer operating status, and conduct a synergy analysis based on the historical data. Use association rule mining to analyze the correlation between the power plant equipment status and the bucket wheel stacker-reclaimer status, and obtain the equipment collaborative working mode.

[0063] It can be understood that the acquisition of historical data involves the status records of power plant equipment and the bucket wheel stacker-reclaimer during their long-term operation. The historical data of power plant equipment includes boiler load, fuel reserve, steam turbine status, power generation power, etc., while the historical data of the bucket wheel stacker-reclaimer includes its transportation efficiency, material grabbing volume, equipment failure records, location information, etc. These data are usually collected in real-time through sensors, data acquisition systems, and monitoring systems and form time series data. Through a comprehensive analysis of these historical data, the operation mode, performance changes, and potential collaborative working rules of the equipment can be deeply understood.

[0064] Next, the synergy analysis explores how the power plant equipment and the bucket wheel stacker-reclaimer states interact with each other by analyzing their mutual relationship. The synergy usually manifests as the impact of the change in one equipment state on the performance of the other equipment. For example, the change in the boiler load of the power plant directly affects the transportation task arrangement of the bucket wheel stacker-reclaimer, and the fault state of the bucket wheel stacker-reclaimer may affect the fuel consumption and power generation efficiency of the power plant. By analyzing the historical data, the interdependence and collaborative working mode between these equipment can be revealed.

[0065] Association rule mining analysis uses data mining techniques to reveal the potential relationships between equipment states. Common association rule mining algorithms include the Apriori algorithm and the FP-growth algorithm, which can discover strong association rules between equipment states from a large amount of historical data. For example, the Apriori algorithm can identify the association rule that "when the boiler load is high, the transportation efficiency of the bucket wheel stacker-reclaimer decreases". Through these association rules, the collaborative working mode between the power plant equipment status and the bucket wheel stacker-reclaimer status can be obtained, providing data support for the collaborative scheduling and optimization of the equipment.

[0066] The device collaborative working mode is obtained by comprehensively analyzing the synergy effect and the results of association rule mining to form a model that can reflect the collaborative work between devices. This model describes how devices affect each other and adjust operation tasks under different device states, and finally achieves the optimal allocation of resources and efficiency.

[0067] Step S240: According to the future predicted values of the power plant device states, the bucket wheel stacker-reclaimer state transition probability matrix, and the device collaborative working mode, use a convolutional neural network to extract features from the data of each dimension of the power plant and the bucket wheel stacker-reclaimer, and use an ensemble learning algorithm for model fusion to construct a power plant-bucket wheel stacker-reclaimer digital twin model.

[0068] In this step, the convolutional neural network can perform automated feature learning on the data of each dimension of the power plant devices (such as boiler load, fuel reserve, power generation power, etc.) and the bucket wheel stacker-reclaimer (such as transportation efficiency, device grabbing volume, fault status, etc.). The convolutional neural network can capture the complex relationships between different dimensions, extract high-level features, and form an efficient representation. Through multiple convolutional layers, pooling layers, and fully connected layers, the network can effectively process various data types (such as time series data, state information, operation efficiency, etc.) and output a set of meaningful feature vectors. These features will be used as important inputs for the digital twin model for subsequent decision-making and optimization.

[0069] Next, the ensemble learning algorithm is used to fuse the output results of different models to improve the accuracy and robustness of the model. Ensemble learning methods, such as XGBoost, LightGBM, or random forest, etc., can reduce the bias and variance of a single model by weighted combining the prediction results of multiple basic models, thereby improving the reliability of the prediction results. Through the ensemble learning algorithm, combining the features extracted from the convolutional neural network and the outputs of other physical models (such as thermodynamics models, mechanical mechanics models, etc.), a comprehensive power plant-bucket wheel stacker-reclaimer digital twin model is formed. This model can not only simulate and predict the behaviors of the power plant and the bucket wheel stacker-reclaimer under different operating states, but also optimize the device collaborative working mode and resource scheduling strategy.

[0070] Furthermore, step S220 includes steps S221 to S223.

[0071] Step S221: Perform state extraction processing according to the bucket wheel stacker-reclaimer operation state information. By using the state switching point detection algorithm to analyze the historical operation data of the bucket wheel stacker-reclaimer, obtain the switching point sequence of each state of the bucket wheel stacker-reclaimer;

[0072] It is understandable that the purpose of state transition point detection is to identify the moments when significant changes occur in the device's operating state. The operating states of the bucket wheel stacker-reclaimer include "normal operation", "equipment failure", "standby", etc. Transitions between different states are usually accompanied by sudden changes or trend changes in certain key indicators (such as material grasping volume, transportation efficiency, equipment temperature, etc.). Therefore, the goal of the state transition point detection algorithm is to automatically identify these change points in order to divide the complex device operation trajectory into clearer state intervals. Commonly used change point detection algorithms include detection algorithms based on gradient changes, change point detection algorithms based on time series analysis, and more complex change point detection based on statistical methods (such as the CUSUM algorithm, Pelt algorithm, etc.). These algorithms can find the significant moments of state changes according to the characteristics of the device state data and mark the transition points in the time series data.

[0073] The generation of the transition point sequence is the output result of the state transition point detection algorithm, which records the transition process of the bucket wheel stacker-reclaimer from one state to another. For example, the bucket wheel stacker-reclaimer may transition from the "normal operation" state to the "fault" state, or return from the "standby" state to the "normal operation" state. These transition point sequences can provide the behavior patterns of the bucket wheel stacker-reclaimer under different operating conditions and provide data support for subsequent modeling analysis.

[0074] Step S222: Perform state transition modeling processing according to the transition point sequence. Model the state change process of the bucket wheel stacker-reclaimer by constructing a hidden Markov model, and use the maximum likelihood estimation algorithm for model training to obtain the probability framework of state transition.

[0075] It should be noted that the probability framework of state transition describes the transition relationship between different states and the possibility of each transition. Through the training of the hidden Markov model, the obtained probability framework can provide a reliable basis for subsequent decision-making support.

[0076] Step S223: Perform approximate probability calculation processing based on the probability framework of state transition. Obtain the state transition probability matrix of the bucket wheel stacker-reclaimer by statistically counting the transition frequencies between states and normalizing them.

[0077] It is understandable that the task of approximate probability calculation is to statistically count the transition frequencies from one state to another. This process requires in-depth analysis of the historical operation data of the bucket wheel stacker-reclaimer (such as material grasping volume, transportation efficiency, equipment failure status, etc.). Through the state transition point sequence in the historical data, the common state transitions of the bucket wheel stacker-reclaimer under different operating modes can be identified. For example, if within a certain period, the bucket wheel stacker-reclaimer often transitions from the "normal operation" state to the "equipment failure" state, then it can be inferred that the frequency of such transitions is relatively high. Based on this statistics, the stability and reliability of the device under specific conditions can be understood.

[0078] Normalization is the conversion of the frequency of state transitions into probabilities. This process ensures that the sum of the probabilities of all state transitions is 1, thus forming a standardized model for further analysis and optimization. The normalized state transition probability matrix reflects the conversion possibilities between different states. This information can help the system identify potential failure risks in advance, schedule spare parts and maintenance resources in a timely manner, and thus avoid unexpected downtime and efficiency losses.

[0079] Furthermore, step S240 includes steps S241 to S244.

[0080] Step S241: Based on the future predicted values of the power plant equipment status, conduct physical process modeling. By combining the thermodynamic model and the energy balance equation, simulate the energy flow and efficiency changes of the equipment within a future time period to obtain the predicted results of the thermodynamic dynamic changes of the power plant equipment.

[0081] It should be noted that physical process modeling is to conduct mathematical modeling on the thermodynamic processes of power plant equipment (such as boilers, steam turbines, etc.) to better predict their future operating states. The operation of power plant equipment involves complex heat energy conversion and flow. The heat input of key equipment such as boilers and the energy output of steam turbines are affected by various factors, such as fuel type, load demand, equipment health status, etc. To accurately predict the future thermodynamic state of equipment, thermodynamic models, such as thermodynamic analysis models based on energy conservation, are needed to describe how heat energy flows inside the equipment and is converted into useful work. These models are usually modeled through energy conservation equations (such as the first law), that is, the relationship between the input energy (such as fuel) of the equipment and the output work. The prediction formula for the thermodynamic dynamic changes of power plant equipment is:

[0082]

[0083] Among them, t represents the moment; U(t) represents the internal energy of the equipment at moment t; Q(t) represents the heat input at moment t; W(t) represents the work output at moment t; represents the mass flow rate of the fluid at moment t; h in (t), h out (t) represent the enthalpy values of the fluid flowing into and leaving the equipment respectively; η(t) represents the thermal efficiency of the equipment at moment t.

[0084] Step S242: Based on the bucket wheel stacker-reclaimer state transition probability matrix and the equipment collaborative working mode, conduct modeling processing. Through mechanical mechanics modeling and mechanical simulation, simulate the motion state and mechanical collaborative effect of the bucket wheel stacker-reclaimer to obtain the simulation results of the mechanical motion state of the bucket wheel stacker-reclaimer.

[0085] First, mechanical mechanics modeling is to model the movement of the bucket wheel stacker-reclaimer through mechanical principles (such as rigid body dynamics, dynamic equations, etc.). The operation of the bucket wheel stacker-reclaimer involves the interaction of multiple mechanical components, such as the drive system, conveyor belt, grab, etc. The interaction between these components directly affects its working efficiency and performance. The goal of the mechanical mechanics model is to describe the movement states of these components, including the force and torque transmission between them. For example, the torque of the drive system is transmitted to the grab, and the grab then transports the material to the designated position. The mechanical relationships involved in this process can be modeled through rigid body mechanics and dynamic equations. Through these mechanical models, it is possible to understand and predict the behavior of the bucket wheel stacker-reclaimer under different operating conditions, especially the movement states during different operation stages such as material grabbing, transportation, and unloading.

[0086] Next, mechanical simulation is to simulate the movement process and synergy effect of the bucket wheel stacker-reclaimer under different states through computer simulation technology. Mechanical simulation can transform the mechanical mechanics model into an operable computational model to simulate the actual movement of the bucket wheel stacker-reclaimer during operation. For example, using finite element method (FEM) or multi-body dynamics (MBD) simulation tools to model each component of the bucket wheel stacker-reclaimer and simulate according to real-time equipment state data (such as equipment failure state, transportation efficiency, etc.) to obtain the movement trajectories and mechanical effects under different states. This process can simulate the complex situations that may occur during the operation of the equipment, such as load changes, equipment failures, speed changes, etc., and predict how these factors affect the overall operation efficiency of the bucket wheel stacker-reclaimer.

[0087] The equipment collaborative working mode refers to the synergy effect between the bucket wheel stacker-reclaimer and other equipment in the power plant (such as conveyor belts, transport vehicles, unloading equipment, etc.). During this process, the state changes of the bucket wheel stacker-reclaimer (such as transportation efficiency, grabbing volume, etc.) will affect the load and efficiency of other equipment, and the working states of other equipment will also feedback to the operation efficiency of the bucket wheel stacker-reclaimer. By introducing the model of equipment collaborative working in the simulation, the interaction between equipment can be considered, and the collaborative effects under different equipment working states can be simulated, so as to optimize the task allocation and operation path between equipment.

[0088] In this step, by comprehensively considering the state transition probability matrix of the bucket wheel stacker-reclaimer and the equipment collaborative working mode, mechanical modeling and simulation are carried out. The finally obtained simulation results of the mechanical movement state can accurately describe the movement behavior of the bucket wheel stacker-reclaimer under different working states and reveal the efficiency changes of the equipment in collaborative working. These results provide data support for subsequent operation scheduling, optimized path planning, and equipment maintenance decision-making. Specifically, the motion equations involved in this embodiment are as follows:

[0089] Motion equations of the bucket wheel stacker-reclaimer:

[0090]

[0091] Synergy effect model equation:

[0092]

[0093] Coupled equation of the kinetic model:

[0094]

[0095] Wherein, M represents the mass matrix, which is used to describe the inertia of each component in the system; represents the acceleration vector; represents the damping matrix; K(x) represents the stiffness matrix; F ext represents the external load received by the bucket wheel stacker during operation; F int represents the interaction force between components; n represents the number of components in the system; i represents the serial number of the component currently participating in the synergy effect; x i represents the state vector of the i-th component; x j represents the state vector of the j-th component; F coupling,i represents the synergy force of the i-th component; M eff represents the effective mass matrix, that is, the mass influence after considering the synergy effect; represents the effective damping matrix, reflecting the additional resistance under the synergy effect; K eff (x) represents the effective stiffness matrix, that is, the stiffness change brought about by considering the collaborative work.

[0096] Step S243: Perform feature extraction based on the prediction results of the thermodynamic dynamic changes and the simulation results of the mechanical motion state, and extract spatio-temporal information from the equipment status, energy efficiency, and mechanical motion path dimensions of the power plant equipment and the bucket wheel stacker through a convolutional neural network to obtain a feature vector;

[0097] It can be understood that the prediction results of the thermodynamic dynamic changes mainly describe the energy flow, efficiency changes, and future states of the equipment (for example, changes in boiler load, fuel consumption, and power generation prediction), while the simulation results of the mechanical motion state focus on the physical motion process of the equipment, including the grabbing ability, transportation efficiency, and equipment status changes of the bucket wheel stacker. Combining these two types of information can comprehensively describe the energy efficiency and physical motion behavior of the equipment in different states, thereby providing data support for subsequent feature extraction and optimization decisions.

[0098] Next, a Convolutional Neural Network (CNN) is used to extract spatio-temporal features from these multi-dimensional data. The Convolutional Neural Network has very strong capabilities in image processing and time-series data analysis. It can extract high-level features from both space (e.g., different dimensions of the device state) and time (e.g., the change of the device state over time). In this step, the Convolutional Neural Network automatically extracts effective spatio-temporal information from the state data of power plant equipment and bucket wheel stackers through multiple convolutional layers and pooling layers. These spatio-temporal information can help capture the temporal dependencies and spatial features between device states, understand how the device changes in time and space, and form a comprehensive representation of the device operation.

[0099] In the Convolutional Neural Network model, the spatio-temporal information not only includes the current value of the device state, but also includes the influence of the device's historical state on the current state. For example, the historical energy efficiency change of the device, the change of the movement path of the bucket wheel stacker, etc. These information can extract features through convolution operations to form a set of feature vectors. These feature vectors contain information in multiple dimensions such as device state, energy efficiency, and mechanical movement path, providing detailed input data for subsequent digital twin modeling, optimization decision-making, and fault prediction. The finally obtained feature vectors will contain multi-dimensional and spatio-temporal information, which can provide basic data for device state prediction, collaborative operation optimization, etc. These feature vectors not only have temporal correlation, but also can reflect the complex relationships between device states.

[0100] Step S244: Perform model fusion and optimization processing according to the feature vectors. By using the ensemble learning algorithm, the output results of the thermodynamic model and the mechanical motion model are comprehensively optimized to obtain the digital twin model of the power plant-bucket wheel stacker.

[0101] It can be understood that ensemble learning is a technique that improves the performance of the overall model by combining the prediction results of multiple models. Common ensemble learning methods include random forest, Gradient Boosting Decision Tree (GBDT), XGBoost, etc. In the digital twin model of the power plant-bucket wheel stacker, the ensemble learning algorithm is used to fuse the output results of the thermodynamic model and the mechanical motion model. These two models respectively model the operation state of the device based on the principles of thermodynamics and mechanics. The thermodynamic model focuses on the prediction of energy flow and efficiency change, while the mechanical motion model focuses on the physical motion state and mechanical synergy effect of the device. By introducing the ensemble learning algorithm, the advantages of these two models can be combined, reducing the error of a single model and improving the accuracy of prediction.

[0102] The process of model fusion involves taking the prediction results of the thermodynamic model and the mechanical motion model as inputs, and performing weighted combination or training through an ensemble learning algorithm, so that the advantages of the two models can complement each other. For example, the XGBoost algorithm can train multiple decision trees and assign different weights to each decision tree, making the final prediction result more accurate and avoiding the limitations of over-relying on a certain model. The ensemble learning algorithm can handle the diversity and complexity between models, ensuring that the outputs of different models can complement each other on the premise of ensuring accuracy, and improving the robustness of the overall system.

[0103] Optimization processing is the core part of ensemble learning. In this step, the performance of the power plant-bucket wheel stacker-reclaimer digital twin model is optimized by performing weighted combination on the results of different models. This process involves fine-tuning the model output to maximize prediction accuracy, reduce system errors, and improve the actual application effect of the system. For example, during the optimization process, the weights of the model may be dynamically adjusted according to the actual operating status of the equipment (such as equipment health status, energy consumption, etc.), ensuring that the digital twin model can adapt to the operation changes of the power plant in real time and make intelligent adjustments and predictions.

[0104] The finally obtained power plant-bucket wheel stacker-reclaimer digital twin model can integrate information from both thermodynamic and mechanical motion aspects, comprehensively predicting the operating status and efficiency changes of the equipment. This model can not only reflect the physical operating status of the equipment, but also take into account its energy efficiency and mechanical synergy effects, providing strong data support for subsequent intelligent scheduling, fault prediction, and operation optimization. Through the digital twin model, the power plant can monitor the operating status of the equipment in real time, predict potential problems in advance and make timely adjustments, reduce resource waste, improve equipment utilization rate, and ensure the efficient and stable operation of the system.

[0105] Furthermore, step S300 includes steps S310 to S340.

[0106] Step S310: Perform transportation task demand prediction processing based on the equipment status information in the power plant-bucket wheel stacker-reclaimer digital twin model, and use the long short-term memory network algorithm to analyze the change trends of fuel reserve and boiler load to obtain the predicted transportation demand;

[0107] Specifically, the application of the long short-term memory network model is realized through the following steps:

[0108] Step S311: Data input: Input historical data (such as fuel reserve, boiler load, etc.) into the long short-term memory network model. These data are presented in the form of time series, and the long short-term memory network model can learn the time dependencies therein.

[0109] Step S312, Feature Learning and Memory: The long short-term memory network controls the transmission of information through its unique gating mechanism (input gate, forget gate, output gate), and can automatically learn and remember long-term dependencies related to transportation tasks. For example, for the relationship between boiler load changes and fuel reserve changes, the long short-term memory network can automatically capture and utilize it during prediction.

[0110] Step S313, Demand Prediction: Through the training of the long short-term memory network, the model can predict the transportation demand within a future period based on the input historical data. For example, predict how much transportation volume is needed in the next few hours, days or weeks to meet the boiler load demand.

[0111] Finally, the predicted transportation demand is the predicted value of the future transportation task given by the long short-term memory network model after analyzing the change trends of fuel reserves and boiler load. This demand reflects the transportation task volume that the bucket wheel stacker-reclaimer needs to complete in the future, and directly affects the allocation of transportation resources, the operation arrangement of the bucket wheel stacker-reclaimer, etc.

[0112] Step S320, According to the transportation demand, combine with the operation ability of the bucket wheel stacker-reclaimer to perform task allocation processing, allocate the task volume of each bucket wheel stacker-reclaimer through the mixed integer programming algorithm, and obtain the specific operation plan of the bucket wheel stacker-reclaimer;

[0113] It should be noted that mixed integer programming (MIP) is an optimization algorithm widely used in resource allocation and scheduling problems. The mixed integer programming algorithm defines decision variables as integers to ensure the operability of task allocation (for example, each bucket wheel stacker-reclaimer can only complete an integer number of tasks), and optimizes task allocation through constraint conditions and objective functions. Specifically, in this step, the goal of the mixed integer programming algorithm is to optimize the allocation of transportation tasks to meet the transportation demand, while considering the operation ability and operation time limitations of the bucket wheel stacker-reclaimer. The objective function of mixed integer programming includes the following aspects:

[0114] Maximize transportation efficiency: Ensure that the task allocation of each bucket wheel stacker-reclaimer can be completed efficiently, and reduce the time of no-load or inefficient operation.

[0115] Minimize task delay: Ensure that transportation tasks are completed within the specified time, and reduce delays caused by unbalanced operation or improper resource scheduling.

[0116] Constraint conditions: Include the operation ability limitation of the bucket wheel stacker-reclaimer (such as the maximum transportation volume of each bucket wheel stacker-reclaimer), operation time limitation (such as the limitation of operation period), and equipment status constraint (such as equipment failure or maintenance).

[0117] By combining the transportation demand with the operation capacity of the bucket wheel stacker-reclaimer, the mixed integer programming algorithm can solve the task volume that each bucket wheel stacker-reclaimer should undertake. The task assignment result generates a specific operation plan for each bucket wheel stacker-reclaimer, ensuring that the load of each device matches its capacity and maximizing the overall efficiency of the system.

[0118] Step S330: Perform path planning processing according to the specific operation plan. Simulate the transportation route of the bucket wheel stacker-reclaimer through the dynamic path planning model, and combine the changes in device status and environmental conditions to obtain the optimal transportation path.

[0119] It can be understood that the dynamic path planning model is based on the shortest path algorithms in graph theory (such as A* algorithm, Dijkstra algorithm, genetic algorithm, etc.), and combines real-time data updated dynamically (such as device status and environmental conditions) to ensure that the path planning still has high adaptability in a changing environment. Specifically, these models will dynamically evaluate the transportation efficiency of different paths while considering factors such as the operation volume and time window, and adjust the path according to the current operating status of the device (such as faults, loads, etc.). The path planning model needs to process in real time the impact of the device's health status, workload, and external environmental factors (such as weather, traffic, etc.) on the transportation path to ensure that the selected transportation path is optimal each time.

[0120] Step S340: Perform loading and unloading efficiency evaluation and device collaborative work processing according to the optimal transportation path. Analyze the efficiency of different paths and collaborative operation plans to obtain an optimized transportation plan.

[0121] It should be noted that this method not only optimizes the transportation path, but also reduces resource waste, reduces the risk of equipment failure, and maximizes the utilization rate of equipment through the precise scheduling of device collaborative operations. In addition, the optimized transportation plan can dynamically adapt to changes in device status and environmental factors, providing more flexible and intelligent operation management, and promoting the power plant to develop in a more efficient and intelligent direction.

[0122] Furthermore, step S400 includes step S410 to step S430.

[0123] Step S410: Perform event definition processing according to the optimized transportation plan. Convert the transportation tasks, loading and unloading processes, and device operating status into discrete events and assign timestamps to obtain a discrete event sequence.

[0124] It can be understood that the purpose of event definition processing is to transform transportation tasks, loading and unloading processes, and equipment operating states into discrete events. In discrete event simulation, an event is the specific moment when the system state changes, usually corresponding to the completion of a specific operation or task. Therefore, every change in transportation tasks, loading and unloading processes, and equipment operating states can be regarded as an event. For example, a bucket wheel reclaimer completes a material grabbing task, or a conveyor belt completes an unloading action, which can both be regarded as "events" in the system. A change in the equipment operating state (such as changing from "normal operation" to "fault" state) can also be regarded as an event. In this step, by modeling these tasks and processes, they are transformed into discrete event objects. Next, the assignment of timestamps is to calibrate the time sequence for each event. A timestamp represents the specific time when an event occurs, and it is a crucial element in discrete event simulation. By assigning timestamps to each event, it can ensure that events occur in the actual time sequence and can simulate the evolution process of the equipment state. For example, a fault event of a certain equipment may occur during the transportation process, and the timestamp of this event will be calibrated as the specific time when the fault occurs. Through timestamps, the occurrence order of each event can be precisely controlled to ensure the time consistency of the simulation process. The discrete event sequence is an ordered set composed of all the above events and their timestamps. This sequence reflects the time sequence relationship of different events occurring in the system. For example, the start and end of transportation tasks and changes in equipment states, etc. The discrete event sequence provides complete time series data for subsequent simulation analysis. By analyzing these events, the performance of the system under different operation plans can be evaluated, such as the execution efficiency of transportation tasks and the operating state of equipment, etc.

[0125] Step S420: Perform event trigger processing based on the digital twin model of the power plant - bucket wheel reclaimer, and dynamically adjust the event occurrence time sequence by combining the changes in the equipment workload, operating environment, and transportation route to obtain a dynamic simulation scenario;

[0126] First of all, event trigger processing is to monitor multiple variables in the system (such as changes in equipment workload, operating environment, and transportation route) to judge in real time whether to trigger certain key events. For example, when the equipment workload exceeds the preset threshold, or the equipment operating state changes (such as changing from "normal operation" to "fault"), these changes may trigger new events, thereby adjusting the equipment operation plan. During this process, the trigger conditions can be dynamically set according to the real-time state of the equipment, and these trigger conditions provide a basis for subsequent event processing.

[0127] The workload of the equipment refers to the working intensity borne by the bucket wheel stacker or other equipment when performing tasks. For example, the load or grabbing volume borne by the bucket wheel stacker during transportation. Changes in the workload will directly affect the operating efficiency of the equipment and the task execution time. When the workload exceeds the load capacity of the equipment, it may cause changes in the operating state of the equipment, trigger fault detection events, or require reallocation of tasks. The system needs to adjust the order of event occurrence according to the real-time workload of the equipment to ensure that each equipment can work under an appropriate load and avoid overload situations.

[0128] Changes in the operating environment refer to external conditions that affect the operation of the equipment, such as weather conditions, the smoothness of the transportation road, etc. For example, adverse weather conditions or traffic problems may cause a decrease in the operating efficiency of the bucket wheel stacker and even delay task execution. Changes in the operating environment may trigger events to adjust the task execution timing, such as changing the transportation route, adjusting task allocation, etc., to adapt to the new environmental conditions. By dynamically adjusting the event occurrence timing, the system can timely respond to these external changes and ensure the smooth progress of the operation tasks.

[0129] Changes in the transportation route refer to the adjustment of the original transportation route due to changes in the equipment state or environmental factors. For example, in some cases, equipment failures or environmental impacts may force the system to re-plan the transportation route. The adjustment of the transportation route will trigger a series of events, such as adjusting equipment scheduling, updating the operation plan, etc. By combining the changes in the transportation route with the event trigger mechanism, it can be ensured that the bucket wheel stacker always selects the most appropriate route to complete the task and optimize the overall operation efficiency.

[0130] Finally, the dynamic simulation scenario refers to the real-time simulation results generated through the above event triggering and timing adjustment. The dynamic simulation scenario can reflect the possible changes in the actual operation process of the system and adjust the operation state, task allocation, transportation route, etc. of the equipment according to the real-time input. This simulation scenario provides real-time data support for subsequent optimization and scheduling to ensure that the system can make a quick response according to the real-time situation and avoid equipment idleness, failures, or inefficient operations.

[0131] Step S430: Perform efficiency evaluation processing according to the discrete event sequence and the dynamic simulation scenario. By constructing a discrete event model and simulating the transportation process under different operation scenarios through the Monte Carlo simulation algorithm, the efficiency simulation results of each scenario are obtained.

[0132] It is understandable that, first of all, the discrete event model is formed by converting factors such as transportation tasks, equipment operation status, and working environment into discrete events and combining the occurrence time sequence of events to form a complete simulation model. This model can reflect the execution of each task during the operation of the power plant and the bucket wheel stacker / reclaimer, as well as the possible state changes of the equipment during the operation process. Through the discrete event model, the system can simulate the execution process of different operation plans in detail and provide key data such as the time sequence information of each event and the task execution status.

[0133] Next, the Monte Carlo simulation algorithm is applied to simulate the transportation process under different operation plans. Monte Carlo simulation is a statistical simulation method based on random sampling, which can simulate complex systems through a large number of random experiments. In this step, the Monte Carlo simulation algorithm can generate a large number of random event sequences according to the discrete event model and simulate the execution of the transportation process based on each sequence. These random experiments consider factors such as changes in equipment status, distribution of transportation tasks, and fluctuations in the working environment. By repeating the simulation multiple times, the efficiency distribution under the operation plan can be obtained, and the performance of different operation plans can be evaluated.

[0134] The specific simulation process includes the following aspects:

[0135] Random event simulation: Through the Monte Carlo simulation algorithm, multiple different event occurrence sequences are generated according to the probability distribution of the discrete event sequence.

[0136] Scheme execution evaluation: Each event sequence corresponds to a different operation plan. During the simulation process, the operation plan will be dynamically adjusted according to the equipment operation status and environmental changes to simulate the execution of transportation tasks.

[0137] Efficiency index calculation: Through multiple simulations, the efficiency indexes (such as completion time, energy consumption, equipment utilization rate, etc.) of each operation plan are calculated to obtain the overall performance of the plan.

[0138] The finally obtained efficiency simulation results are the evaluation results of different operation plans, showing the efficiency of each operation plan under different conditions. These results can be used to compare the advantages and disadvantages of each plan and help the power plant select the optimal operation plan. Through this simulation, the system can deeply analyze the bottlenecks in the transportation process, optimize resource allocation, reduce time and energy consumption waste in the operation, and thus improve the overall operation efficiency.

[0139] Furthermore, step S500 includes steps S510 to S530.

[0140] Step S510: Set the objective function according to the efficiency simulation results. By analyzing the simulation results, quantify the transportation efficiency, equipment failure rate, energy consumption, and environmental impact to obtain the quantified indexes of the optimized objective function;

[0141] It should be noted that when setting the objective function, several main optimization objectives need to be considered:

[0142] Transportation efficiency: This objective mainly focuses on the efficiency of the material transportation process, which is usually quantified by indicators such as the time to complete the task and the ratio of transportation volume to time. Preferably, the transportation efficiency can be reflected by calculating the transportation volume per unit time or the task completion time.

[0143] Equipment failure rate: The equipment failure rate is an important indicator to measure the reliability of the equipment. Usually, the probability of equipment failure within a certain period of time is calculated. By simulating the occurrence of equipment failures in the results, quantitative data on the equipment failure rate can be obtained, thus reflecting the overall stability of the system.

[0144] Energy consumption: Energy consumption mainly refers to the energy consumed during the transportation process, which is usually quantified by the energy consumption per unit of transportation volume or the total energy consumption of the entire system. Through the efficiency simulation results, the impact of different operation plans on energy use can be evaluated, and then the energy utilization in the operation process can be optimized.

[0145] Environmental impact: The environmental impact is a key indicator to evaluate the sustainability of the operation plan, usually including factors such as carbon emissions and noise. The simulation results can provide data on the environmental impact of different plans, thus helping to select the most environmentally friendly operation method.

[0146] Step S520: Perform weighted combination processing according to the quantitative indicators of the optimization objective function, determine the weights of each objective through the particle swarm optimization algorithm, and calculate the comprehensive effectiveness of each operation plan to obtain the weighted objective value;

[0147] It can be understood that the weighted combination processing combines different optimization objectives (such as transportation efficiency, equipment failure rate, energy consumption, and environmental impact) to form a comprehensive objective function. In multi-objective optimization problems, the relative importance of each objective may be different, so it is necessary to assign a weight to each objective. The process of weighted combination is to merge the quantitative indicators of each optimization objective into a unified objective function by assigning weights. The key to this process lies in how to assign the weights of different objectives according to actual needs and priorities.

[0148] The Particle Swarm Optimization (PSO) algorithm is an optimization algorithm based on swarm intelligence and is widely used in multi-objective optimization problems. In this step, the task of the PSO algorithm is to determine the weights of each objective. The PSO algorithm finds the optimal weight combination by simulating the movement and search process of a group of particles, so that the value of the comprehensive objective function reaches the optimum. Each particle represents a potential weight combination scheme. The particles move in the search space and adjust their positions according to the fitness function (i.e., the value of the comprehensive objective function). Through continuous iteration, the particle swarm gradually converges to the globally optimal weight combination. Through the PSO algorithm, the weights of each objective can be automatically adjusted to achieve the optimal trade-off between objectives.

[0149] Step S530: Perform a solution process based on the weighted objective values, use the simulated annealing algorithm to find the optimal solution in the multi-objective space, and generate a specific operation plan based on the optimal solution.

[0150] It should be noted that, first of all, the simulated annealing algorithm is a heuristic global optimization algorithm inspired by the physical annealing process. The simulated annealing algorithm simulates the process of a substance from high temperature to low temperature, gradually reducing the "temperature" of the system during the search process, so that the search process changes from exploring the global optimal solution to gradually converging to the local optimal solution. For multi-objective optimization problems, the simulated annealing algorithm can effectively avoid being trapped in the local optimal solution. Through random perturbation and acceptance probability strategies, it conducts global search to find the optimal trade-off between multiple objectives.

[0151] The multi-objective space refers to a high-dimensional space formed after considering multiple optimization objectives such as transportation efficiency, equipment failure rate, energy consumption, and environmental impact. In this space, each point represents a possible operation plan, including the weighted values of each objective and the corresponding quantitative indicators. The simulated annealing algorithm searches for the optimal solution by iterating in this multi-dimensional space. The algorithm gradually approaches the optimal solution by accepting better solutions and accepting worse solutions with a certain probability (to avoid being trapped in the local optimum).

[0152] In the specific solution process, the simulated annealing algorithm is optimized through the following steps:

[0153] Step S531: Initial solution selection: Start from a random initial operation plan and calculate its weighted objective value (comprehensive efficiency).

[0154] Step S532: Neighborhood search: Generate a new neighborhood solution by perturbing the current solution (i.e., the operation plan). For example, adjust the allocation of equipment tasks, the selection of transportation routes, etc.

[0155] Step S533, Acceptance Criterion: Determine whether to accept the new solution by calculating the weighted objective value of the new solution. If the comprehensive performance of the new solution is better than the current solution, accept the new solution; if the new solution is worse, accept the solution with a certain probability to avoid falling into a local optimal solution.

[0156] Step S534, Temperature Decay: As the algorithm iterates, gradually reduce the "temperature" to decrease the probability of accepting a worse solution, so that the search process focuses more on the local optimal solution.

[0157] Step S535, Termination Condition: When the predetermined number of iterations is reached or the temperature drops to the set threshold, the algorithm stops and outputs the final optimal solution.

[0158] The optimal solution represents the best trade-off scheme among various optimization objectives in the multi-objective space. This optimal solution can ensure that the power plant achieves an optimal balance in aspects such as transportation efficiency, equipment failure rate, energy consumption, and environmental impact, meeting the overall optimization requirements of the system.

[0159] Finally, generate a specific operation plan based on the optimal solution to formulate the actual operation task arrangement. For example, adjust the transportation task volume of each bucket wheel reclaimer, the operation path of the equipment, and the arrangement of the operation time period according to the optimal solution. This operation plan will be used as a guide in the actual operation of the power plant to ensure the optimal performance of the system under multiple objectives.

[0160] Embodiment 2:

[0161] As Figure 2 shown, this embodiment provides an unmanned intelligent operation system for a bucket wheel reclaimer in a power plant based on an AI algorithm. The system includes:

[0162] An acquisition module 901, configured to acquire the operation state information of the power plant and the information of the bucket wheel reclaimer. The power plant state information includes the fuel reserve, boiler load, steam turbine state, and power generation power. The bucket wheel reclaimer information includes the position information, transportation efficiency, material grabbing amount, and equipment failure state of the bucket wheel reclaimer;

[0163] A modeling module 902, configured to construct a digital twin model of the power plant - bucket wheel reclaimer by performing trend analysis and state change modeling on the equipment state of the power plant and the operation state of the bucket wheel reclaimer according to the operation state information of the power plant and the information of the bucket wheel reclaimer;

[0164] An analysis module 903, performing a correlation analysis on the fuel reserve of the power plant and the transportation tasks of the bucket wheel reclaimer based on the digital twin model of the power plant - bucket wheel reclaimer, simulating the transportation route through a path planning algorithm, and evaluating the loading and unloading efficiency and the equipment cooperation situation in combination with real-time state data to obtain an optimized transportation plan;

[0165] The simulation module 904 is used to perform discrete event simulation processing according to the optimized transportation plan. By converting the transportation process into discrete events and combining real-time device status data for data format conversion and event-driven simulation, an efficiency simulation result is obtained;

[0166] The optimization module 905 performs optimization processing based on the efficiency simulation result. By setting an objective function, which includes maximizing transportation efficiency, minimizing equipment failure rate, optimizing energy consumption, and minimizing environmental impact, using a multi-objective optimization algorithm to weight and combine each objective, and solving for the optimal solution, an operation plan is obtained.

[0167] In some embodiments disclosed in the present application, the modeling module 902 includes:

[0168] The first modeling unit is used to perform equipment status trend analysis based on the power plant operation status information. By using the autoregressive integrated moving average algorithm to analyze the trend of the fuel reserve, boiler load, steam turbine status, and power generation power of the power plant, future predicted values of the power plant equipment status are obtained;

[0169] The second modeling unit is used to perform state change modeling based on the bucket wheel stacker / reclaimer operation status information. By constructing a hidden Markov model to model the state change of the bucket wheel stacker / reclaimer and simulating the operation state change of the bucket wheel stacker / reclaimer, a state transition probability matrix of the bucket wheel stacker / reclaimer is obtained;

[0170] The third modeling unit is used to obtain historical data of the power plant equipment status and the bucket wheel stacker / reclaimer operation status, and perform synergy effect analysis based on the historical data. Association rule mining is used to analyze the correlation between the power plant equipment status and the bucket wheel stacker / reclaimer status, and an equipment collaborative working mode is obtained;

[0171] The fourth modeling unit is used to extract features from the data of each dimension of the power plant and the bucket wheel stacker / reclaimer according to the future predicted values of the power plant equipment status, the state transition probability matrix of the bucket wheel stacker / reclaimer, and the equipment collaborative working mode, and use an ensemble learning algorithm for model fusion to construct a power plant - bucket wheel stacker / reclaimer digital twin model.

[0172] In some embodiments disclosed in the present application, the second modeling unit includes:

[0173] The fifth modeling unit is used to perform state extraction processing based on the bucket wheel stacker / reclaimer operation status information. By using the state switching point detection algorithm to analyze the historical operation data of the bucket wheel stacker / reclaimer, a switching point sequence of each state of the bucket wheel stacker / reclaimer is obtained;

[0174] The sixth modeling unit is used to perform state transition modeling processing based on the switching point sequence. By constructing a hidden Markov model to model the state change process of the bucket wheel stacker / reclaimer and using the maximum likelihood estimation algorithm for model training, a probability framework of state transition is obtained;

[0175] The seventh modeling unit performs a rough probability calculation process based on a probability framework of state transition. By statistically counting the transition frequencies between states and normalizing them, a state transition probability matrix of the bucket wheel stacker-reclaimer is obtained.

[0176] Embodiment 3:

[0177] Corresponding to the above method embodiment, in this embodiment, an unmanned intelligent operation device for a power plant bucket wheel stacker-reclaimer based on an AI algorithm is also provided. An unmanned intelligent operation device for a power plant bucket wheel stacker-reclaimer based on an AI algorithm described below can be mutually corresponding and referred to with an unmanned intelligent operation method for a power plant bucket wheel stacker-reclaimer based on an AI algorithm described above.

[0178] Figure 3 It is a block diagram of an unmanned intelligent operation device 800 for a power plant bucket wheel stacker-reclaimer based on an AI algorithm shown according to an exemplary embodiment. As Figure 3 shown, the unmanned intelligent operation device 800 for a power plant bucket wheel stacker-reclaimer based on an AI algorithm may include: a processor 801, a memory 802. The unmanned intelligent operation device 800 for a power plant bucket wheel stacker-reclaimer based on an AI algorithm may further include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0179] Among them, the processor 801 is used to control the overall operation of the unmanned intelligent operation device 800 of the power plant bucket wheel based on the AI algorithm to complete all or part of the steps in the above-mentioned unmanned intelligent operation method of the power plant bucket wheel based on the AI algorithm. The memory 802 is used to store various types of data to support the operation of the unmanned intelligent operation device 800 of the power plant bucket wheel based on the AI algorithm. These data may include, for example, instructions for any application program or method operating on the unmanned intelligent operation device 800 of the power plant bucket wheel based on the AI algorithm, as well as application program-related data, such as contact data, sent and received messages, pictures, audio, video, and so on. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, magnetic disk or optical disc. The multimedia component 803 may include a screen and an audio component. Among them, the screen can be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, and the microphone is used to receive external audio signals. The received audio signals can be further stored in the memory 802 or sent through the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above other interface modules can be a keyboard, a mouse, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the unmanned intelligent operation device 800 of the power plant bucket wheel based on the AI algorithm and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them. Therefore, the corresponding communication component 805 may include: a Wi-Fi module, a Bluetooth module, an NFC module.

[0180] In an exemplary embodiment, an unmanned intelligent operation device 800 for a power plant bucket wheel based on an AI algorithm can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the above-mentioned unmanned intelligent operation method for a power plant bucket wheel based on an AI algorithm.

[0181] In another exemplary embodiment, there is also provided a computer-readable storage medium including program instructions, and when the program instructions are executed by a processor, the steps of the above-mentioned unmanned intelligent operation method for a power plant bucket wheel based on an AI algorithm are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above program instructions can be executed by the processor 801 of an unmanned intelligent operation device 800 for a power plant bucket wheel based on an AI algorithm to complete the above-mentioned unmanned intelligent operation method for a power plant bucket wheel based on an AI algorithm.

[0182] As mentioned above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. An unmanned intelligent operation method for the bucket wheel machine in a power plant based on AI algorithms, characterized in that, Including: Obtain the operating status information of the power plant and the information of the bucket wheel stacker-reclaimer. The power plant status information includes fuel reserve, boiler load, steam turbine status, and power generation capacity. The information of the bucket wheel stacker-reclaimer includes the position information, transportation efficiency, material grabbing amount, and equipment failure status of the bucket wheel stacker-reclaimer; According to the operating status information of the power plant and the information of the bucket wheel stacker-reclaimer, through trend analysis and state change modeling of the equipment status of the power plant and the operating status of the bucket wheel stacker-reclaimer, construct a digital twin model of the power plant-bucket wheel stacker-reclaimer; Based on the digital twin model of the power plant-bucket wheel stacker-reclaimer, conduct an association analysis of the fuel reserve of the power plant and the transportation tasks of the bucket wheel stacker-reclaimer, simulate the transportation route through the path planning algorithm, and evaluate the loading and unloading efficiency and the collaborative working condition of the equipment by combining real-time status data to obtain an optimized transportation plan; Conduct discrete event simulation processing according to the optimized transportation plan. By converting the transportation process into discrete events and combining real-time equipment status data for data format conversion and event-driven simulation, obtain an efficiency simulation result; Based on the efficiency simulation result, conduct optimization processing. By setting the objective function, the objective function includes maximizing transportation efficiency, minimizing equipment failure rate, optimizing energy consumption, and minimizing environmental impact. Use the multi-objective optimization algorithm to perform weighted combination of each objective and solve for the optimal solution to obtain an operation plan.

2. The method for unmanned intelligent operation of the bucket wheel stacker-reclaimer in a power plant based on the AI algorithm according to claim 1, wherein, According to the operating status information of the power plant and the information of the bucket wheel stacker-reclaimer, through trend analysis and state change modeling of the equipment status of the power plant and the operating status of the bucket wheel stacker-reclaimer, construct a digital twin model of the power plant-bucket wheel stacker-reclaimer, including: Conduct equipment status trend analysis according to the operating status information of the power plant. Through using the autoregressive integrated moving average algorithm to analyze the trend of the fuel reserve, boiler load, steam turbine status, and power generation capacity of the power plant, obtain the future predicted values of the equipment status of the power plant; Conduct state change modeling according to the operating status information of the bucket wheel stacker-reclaimer. By constructing a hidden Markov model to model the state change of the bucket wheel stacker-reclaimer and simulate the change of the operating status of the bucket wheel stacker-reclaimer, obtain the state transition probability matrix of the bucket wheel stacker-reclaimer; Obtain the historical data of the equipment status of the power plant and the operating status of the bucket wheel stacker-reclaimer, and conduct collaborative effect analysis based on the historical data. Use association rule mining to analyze the correlation between the equipment status of the power plant and the status of the bucket wheel stacker-reclaimer to obtain the equipment collaborative working mode; According to the future predicted values of the equipment status of the power plant, the state transition probability matrix of the bucket wheel stacker-reclaimer, and the equipment collaborative working mode, use a convolutional neural network to extract features from the data of each dimension of the power plant and the bucket wheel stacker-reclaimer, and use the ensemble learning algorithm for model fusion to construct a digital twin model of the power plant-bucket wheel stacker-reclaimer.

3. The method for unmanned intelligent operation of the bucket wheel stacker-reclaimer in a power plant based on the AI algorithm according to claim 2, characterized in that, Conduct state change modeling according to the operating status information of the bucket wheel stacker-reclaimer. By constructing a hidden Markov model to model the state change of the bucket wheel stacker-reclaimer and simulate the change of the operating status of the bucket wheel stacker-reclaimer, obtain the state transition probability matrix of the bucket wheel stacker-reclaimer, including: Conduct state extraction processing according to the operating status information of the bucket wheel stacker-reclaimer. By using the state switching point detection algorithm to analyze the historical operation data of the bucket wheel stacker-reclaimer, obtain the switching point sequence of each state of the bucket wheel stacker-reclaimer; Perform state transition modeling processing according to the switching point sequence, model the state change process of the bucket wheel stacker-reclaimer by constructing a hidden Markov model, and use the maximum likelihood estimation algorithm for model training to obtain the probability framework of state transition; Perform approximate probability calculation processing based on the probability framework of state transition. By counting the transition frequencies between states and normalizing them, obtain the state transition probability matrix of the bucket wheel stacker-reclaimer.

4. The method for unmanned intelligent operation of the bucket wheel stacker-reclaimer in a power plant based on the AI algorithm according to claim 2, wherein, According to the future prediction value of the power plant equipment state, the state transition probability matrix of the bucket wheel stacker-reclaimer, and the equipment collaborative working mode, use a convolutional neural network to extract features from the data of each dimension of the power plant and the bucket wheel stacker-reclaimer, and use an ensemble learning algorithm for model fusion to construct a power plant-bucket wheel stacker-reclaimer digital twin model, including: Perform physical process modeling according to the future prediction value of the power plant equipment state. By combining the thermodynamic model and the energy balance equation, simulate the energy flow and efficiency change of the equipment in the future time period to obtain the prediction result of the thermodynamic dynamic change of the power plant equipment; Perform modeling processing according to the state transition probability matrix of the bucket wheel stacker-reclaimer and the equipment collaborative working mode. Through mechanical mechanics modeling and mechanical simulation, simulate the motion state and mechanical collaborative effect of the bucket wheel stacker-reclaimer to obtain the simulation result of the mechanical motion state of the bucket wheel stacker-reclaimer; Perform feature extraction according to the prediction result of the thermodynamic dynamic change and the simulation result of the mechanical motion state. Through a convolutional neural network, extract spatio-temporal information from the dimensions of the equipment state, energy efficiency, and mechanical motion path of the power plant equipment and the bucket wheel stacker-reclaimer to obtain a feature vector; Perform model fusion and optimization processing according to the feature vector. By using an ensemble learning algorithm to comprehensively optimize the output results of the thermodynamic model and the mechanical motion model, obtain the power plant-bucket wheel stacker-reclaimer digital twin model.

5. The method for unmanned intelligent operation of the bucket wheel stacker-reclaimer in a power plant based on the AI algorithm according to claim 1, characterized in that, Based on the power plant-bucket wheel stacker-reclaimer digital twin model, perform correlation analysis of the fuel reserve of the power plant and the transportation task of the bucket wheel stacker-reclaimer. By simulating the transportation route through a path planning algorithm and combining real-time state data to evaluate the loading and unloading efficiency and equipment collaborative working conditions, obtain an optimized transportation plan, including: Perform transportation task demand prediction processing according to the equipment state information in the power plant-bucket wheel stacker-reclaimer digital twin model. Use the long short-term memory network algorithm to analyze the change trends of the fuel reserve and the boiler load to obtain the predicted transportation demand; Perform task allocation processing according to the transportation demand, combined with the operation ability of the bucket wheel stacker-reclaimer. By using a mixed integer programming algorithm to allocate the task volume of each bucket wheel stacker-reclaimer, obtain the specific operation plan of the bucket wheel stacker-reclaimer; Perform path planning processing according to the specific operation plan. By simulating the transportation route of the bucket wheel stacker-reclaimer through a dynamic path planning model and combining the equipment state change and environmental conditions, obtain the optimal transportation path; Perform loading and unloading efficiency evaluation and equipment collaborative working processing according to the optimal transportation path. By analyzing the efficiency of different paths and collaborative operation schemes, obtain an optimized transportation plan.

6. The method for unmanned intelligent operation of a power plant bucket wheel machine based on an AI algorithm according to claim 1, characterized in that, Perform discrete event simulation processing according to the optimized transportation plan. By converting the transportation process into discrete events and combining real-time equipment state data for data format conversion and event-driven simulation, obtain the efficiency simulation result, including: Event definition processing is performed according to the optimized transportation plan. By converting transportation tasks, loading and unloading processes, and equipment operating states into discrete events and assigning timestamps, a discrete event sequence is obtained; Event triggering processing is performed according to the power plant - bucket wheel stacker / reclaimer digital twin model. By combining the workload of the equipment, the operating environment, and changes in the transportation route, the timing of event occurrence is dynamically adjusted to obtain a dynamic simulation scenario; Efficiency evaluation processing is performed according to the discrete event sequence and the dynamic simulation scenario. By constructing a discrete event model and simulating the transportation process under different operation plans through the Monte Carlo simulation algorithm, the efficiency simulation results of each plan are obtained.

7. The method for unmanned intelligent operation of a power plant bucket wheel machine based on the AI algorithm according to claim 1, characterized in that, Optimization processing is performed based on the efficiency simulation results. By setting an objective function, the objective function includes maximizing transportation efficiency, minimizing equipment failure rate, optimizing energy consumption, and minimizing environmental impact. The multi-objective optimization algorithm is used to perform weighted combination on each objective and solve for the optimal solution to obtain an operation plan, including: The objective function is set according to the efficiency simulation results. By analyzing the simulation results to quantify transportation efficiency, equipment failure rate, energy consumption, and environmental impact, the quantitative indicators for optimizing the objective function are obtained; Weighted combination processing is performed according to the quantitative indicators of the optimized objective function. By using the particle swarm optimization algorithm to determine the weights of each objective and calculate the comprehensive effectiveness of each operation plan, the weighted objective value is obtained; Solution processing is performed based on the weighted objective value. The simulated annealing algorithm is used to find the optimal solution in the multi-objective space, and a specific operation plan is generated based on the optimal solution.

8. An unmanned intelligent operation system for a power plant bucket wheel stacker / reclaimer based on AI algorithms, characterized in that, Including: An acquisition module for acquiring the power plant operating state information and the bucket wheel stacker / reclaimer information. The power plant state information includes fuel reserve, boiler load, steam turbine state, and power generation power. The bucket wheel stacker / reclaimer information includes the position information, transportation efficiency, material grabbing quantity, and equipment failure state of the bucket wheel stacker / reclaimer; A modeling module for constructing a power plant - bucket wheel stacker / reclaimer digital twin model according to the power plant operating state information and the bucket wheel stacker / reclaimer information by performing trend analysis and state change modeling on the equipment state of the power plant and the operating state of the bucket wheel stacker / reclaimer; An analysis module for performing correlation analysis between the fuel reserve of the power plant and the transportation tasks of the bucket wheel stacker / reclaimer based on the power plant - bucket wheel stacker / reclaimer digital twin model, simulating the transportation route through the path planning algorithm, and evaluating the loading and unloading efficiency and equipment collaborative working conditions in combination with real-time state data to obtain an optimized transportation plan; A simulation module for performing discrete event simulation processing according to the optimized transportation plan. By converting the transportation process into discrete events and performing data format conversion and event-driven simulation in combination with real-time equipment state data, the efficiency simulation results are obtained; An optimization module for performing optimization processing based on the efficiency simulation results. By setting an objective function, the objective function includes maximizing transportation efficiency, minimizing equipment failure rate, optimizing energy consumption, and minimizing environmental impact. The multi-objective optimization algorithm is used to perform weighted combination on each objective and solve for the optimal solution to obtain an operation plan.

9. The unmanned intelligent operation system of the power plant bucket wheel machine based on the AI algorithm according to claim 8, characterized in that, The modeling module includes: The first modeling unit is used to perform equipment status trend analysis based on the power plant operation status information. By using the autoregressive integrated moving average algorithm, trend analysis is carried out on the fuel reserve, boiler load, steam turbine status, and power generation of the power plant to obtain the future prediction values of the power plant equipment status; The second modeling unit is used to perform status change modeling based on the bucket wheel stacker-reclaimer operation status information. By constructing a hidden Markov model, the status change of the bucket wheel stacker-reclaimer is modeled, and the operation status change of the bucket wheel stacker-reclaimer is simulated to obtain the bucket wheel stacker-reclaimer status transition probability matrix; The third modeling unit is used to obtain the historical data of the power plant equipment status and the bucket wheel stacker-reclaimer operation status, and perform synergy analysis based on the historical data. Association rule mining is used to analyze the correlation between the power plant equipment status and the bucket wheel stacker-reclaimer status to obtain the equipment collaborative working mode; The fourth modeling unit is used to perform feature extraction on the data of each dimension of the power plant and the bucket wheel stacker-reclaimer according to the future prediction values of the power plant equipment status, the bucket wheel stacker-reclaimer status transition probability matrix, and the equipment collaborative working mode, and use the ensemble learning algorithm for model fusion to construct a power plant-bucket wheel stacker-reclaimer digital twin model.

10. The unmanned intelligent operation system of the power plant bucket wheel machine based on the AI algorithm according to claim 9, characterized in that, The second modeling unit includes: The fifth modeling unit is used to perform status extraction processing based on the bucket wheel stacker-reclaimer operation status information. By using the state switching point detection algorithm to analyze the historical operation data of the bucket wheel stacker-reclaimer, the switching point sequence of each status of the bucket wheel stacker-reclaimer is obtained; The sixth modeling unit is used to perform status transition modeling processing based on the switching point sequence. By constructing a hidden Markov model to model the status change process of the bucket wheel stacker-reclaimer, and using the maximum likelihood estimation algorithm for model training to obtain the probability framework of status transition; The seventh modeling unit performs approximate probability calculation processing based on the probability framework of status transition. By statistically counting the transition frequencies between states and normalizing them, the bucket wheel stacker-reclaimer status transition probability matrix is obtained.

Images